MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling
This work addresses the need for precise, melody-preserving lyric editing in singing voice, which is important for music production and audio editing applications.
MeloDISinger achieves state-of-the-art performance in text-based singing voice editing by using a flow-matching model with explicit duration control and melody-aware duration allocation, outperforming prior methods in objective and subjective evaluations.
Text-based singing voice editing (SVE) aims to revise sung lyrics while preserving the original melody, total duration, and non-edited regions. In this paper, we propose MeloDISinger, a flow-matching-based SVE model for melody-aware and duration-preserving editing. Its core module, MeloDRP, predicts fixed-budget duration ratios, enabling explicit span-wise duration control. For melody-aware duration allocation, MeloDRP fuses phonetic cues with pseudo-MIDI melodic context through cross-attention, while temporal-overlap supervision encourages soft phoneme--note correspondences. We further use a flow-matching mel decoder for audio infilling to synthesize edited regions while preserving surrounding context. In addition, we introduce a duration-aware edited-lyric generation pipeline using WhisperX and an LLM to construct feasible evaluation scenarios. Experiments demonstrate state-of-the-art performance in both objective and subjective evaluations.